make-pr-easy-to-review

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the GitHub CLI (gh) and Git to fetch branch data and manipulate commit history.
  • [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it processes untrusted input from PR metadata and commit history. 1. Ingestion points: PR descriptions and commit messages retrieved from GitHub. 2. Boundary markers: None specified. 3. Capability inventory: Use of git history rewriting and PR description updates. 4. Sanitization: Includes a manual verification step comparing tree hashes (git rev-parse) to ensure code behavior remains identical.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 03:44 PM
Security Audit — agent-trust-hub — make-pr-easy-to-review